File size: 6,122 Bytes
d26a270 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 | {
"best_global_step": 115,
"best_metric": 2.282820701599121,
"best_model_checkpoint": "tiny_bert_rand_50_v2_stsb/checkpoint-115",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 230,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 4.757383823394775,
"learning_rate": 4.9e-05,
"loss": 3.577,
"step": 23
},
{
"epoch": 1.0,
"eval_combined_score": 0.11416083891115508,
"eval_loss": 2.3197340965270996,
"eval_pearson": 0.12061995262322296,
"eval_runtime": 0.4408,
"eval_samples_per_second": 3403.103,
"eval_spearmanr": 0.10770172519908719,
"eval_steps_per_second": 13.612,
"step": 23
},
{
"epoch": 2.0,
"grad_norm": 10.133877754211426,
"learning_rate": 4.8e-05,
"loss": 2.0557,
"step": 46
},
{
"epoch": 2.0,
"eval_combined_score": 0.12699515116533755,
"eval_loss": 2.4031293392181396,
"eval_pearson": 0.12910611175823888,
"eval_runtime": 0.5154,
"eval_samples_per_second": 2910.631,
"eval_spearmanr": 0.1248841905724362,
"eval_steps_per_second": 11.643,
"step": 46
},
{
"epoch": 3.0,
"grad_norm": 8.422947883605957,
"learning_rate": 4.7e-05,
"loss": 1.8854,
"step": 69
},
{
"epoch": 3.0,
"eval_combined_score": 0.2013417461648624,
"eval_loss": 2.3712551593780518,
"eval_pearson": 0.203885354732845,
"eval_runtime": 0.4923,
"eval_samples_per_second": 3047.172,
"eval_spearmanr": 0.19879813759687975,
"eval_steps_per_second": 12.189,
"step": 69
},
{
"epoch": 4.0,
"grad_norm": 11.295201301574707,
"learning_rate": 4.600000000000001e-05,
"loss": 1.7118,
"step": 92
},
{
"epoch": 4.0,
"eval_combined_score": 0.2468785884457752,
"eval_loss": 2.3257670402526855,
"eval_pearson": 0.24741486493265863,
"eval_runtime": 0.4527,
"eval_samples_per_second": 3313.331,
"eval_spearmanr": 0.24634231195889175,
"eval_steps_per_second": 13.253,
"step": 92
},
{
"epoch": 5.0,
"grad_norm": 6.806567668914795,
"learning_rate": 4.5e-05,
"loss": 1.4486,
"step": 115
},
{
"epoch": 5.0,
"eval_combined_score": 0.26071507127769444,
"eval_loss": 2.282820701599121,
"eval_pearson": 0.263404431762189,
"eval_runtime": 0.4792,
"eval_samples_per_second": 3130.148,
"eval_spearmanr": 0.25802571079319986,
"eval_steps_per_second": 12.521,
"step": 115
},
{
"epoch": 6.0,
"grad_norm": 8.495306968688965,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.2898,
"step": 138
},
{
"epoch": 6.0,
"eval_combined_score": 0.26830817042733024,
"eval_loss": 2.7079834938049316,
"eval_pearson": 0.2622377772014732,
"eval_runtime": 0.4751,
"eval_samples_per_second": 3157.388,
"eval_spearmanr": 0.27437856365318725,
"eval_steps_per_second": 12.63,
"step": 138
},
{
"epoch": 7.0,
"grad_norm": 13.502508163452148,
"learning_rate": 4.3e-05,
"loss": 1.0578,
"step": 161
},
{
"epoch": 7.0,
"eval_combined_score": 0.28573879609613473,
"eval_loss": 2.650726318359375,
"eval_pearson": 0.28150603591850215,
"eval_runtime": 0.4542,
"eval_samples_per_second": 3302.865,
"eval_spearmanr": 0.2899715562737673,
"eval_steps_per_second": 13.211,
"step": 161
},
{
"epoch": 8.0,
"grad_norm": 7.592569351196289,
"learning_rate": 4.2e-05,
"loss": 0.8953,
"step": 184
},
{
"epoch": 8.0,
"eval_combined_score": 0.2609240583203716,
"eval_loss": 2.863307237625122,
"eval_pearson": 0.25851307223546727,
"eval_runtime": 0.5148,
"eval_samples_per_second": 2913.731,
"eval_spearmanr": 0.2633350444052759,
"eval_steps_per_second": 11.655,
"step": 184
},
{
"epoch": 9.0,
"grad_norm": 29.740528106689453,
"learning_rate": 4.1e-05,
"loss": 0.7584,
"step": 207
},
{
"epoch": 9.0,
"eval_combined_score": 0.2446564587157261,
"eval_loss": 3.175959587097168,
"eval_pearson": 0.24206257082189755,
"eval_runtime": 0.4631,
"eval_samples_per_second": 3238.968,
"eval_spearmanr": 0.24725034660955467,
"eval_steps_per_second": 12.956,
"step": 207
},
{
"epoch": 10.0,
"grad_norm": 10.117051124572754,
"learning_rate": 4e-05,
"loss": 0.6589,
"step": 230
},
{
"epoch": 10.0,
"eval_combined_score": 0.26549244920567694,
"eval_loss": 3.0019023418426514,
"eval_pearson": 0.26127781004194356,
"eval_runtime": 0.4522,
"eval_samples_per_second": 3316.9,
"eval_spearmanr": 0.2697070883694104,
"eval_steps_per_second": 13.268,
"step": 230
},
{
"epoch": 10.0,
"step": 230,
"total_flos": 1507548205378560.0,
"train_loss": 1.5338545426078465,
"train_runtime": 43.6565,
"train_samples_per_second": 6584.362,
"train_steps_per_second": 26.342
}
],
"logging_steps": 1,
"max_steps": 1150,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 5
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1507548205378560.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|